{"id":"https://openalex.org/W4285590546","doi":"https://doi.org/10.1142/s0218194022500449","title":"Clean and Learn: Improving Robustness to Spurious Solutions in API Question Answering","display_name":"Clean and Learn: Improving Robustness to Spurious Solutions in API Question Answering","publication_year":2022,"publication_date":"2022-07-01","ids":{"openalex":"https://openalex.org/W4285590546","doi":"https://doi.org/10.1142/s0218194022500449"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194022500449","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500449","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084266381","display_name":"Shuai Yuan","orcid":"https://orcid.org/0000-0002-7169-2505"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yuan","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0002-7169-2505","affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066145804","display_name":"Haozhe Qin","orcid":"https://orcid.org/0009-0006-4398-1525"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haozhe Qin","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033286111","display_name":"Xiaodong Gu","orcid":"https://orcid.org/0000-0002-0529-6408"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Gu","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045672909","display_name":"Beijun Shen","orcid":"https://orcid.org/0000-0001-8370-3956"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Beijun Shen","raw_affiliation_strings":["School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China"],"raw_orcid":"https://orcid.org/0000-0001-8370-3956","affiliations":[{"raw_affiliation_string":"School of Software, Shanghai Jiao Tong University, Shanghai, P. R. China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045672909"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.6381,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.73640797,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"32","issue":"07","first_page":"1101","last_page":"1123"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.8489439487457275},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8024023771286011},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7893569469451904},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6934771537780762},{"id":"https://openalex.org/keywords/application-programming-interface","display_name":"Application programming interface","score":0.6714671850204468},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5008647441864014},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49982261657714844},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4814528822898865},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.4439719021320343},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.42427128553390503},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4165293872356415},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4105226993560791},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17999666929244995}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.8489439487457275},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8024023771286011},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7893569469451904},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6934771537780762},{"id":"https://openalex.org/C99613125","wikidata":"https://www.wikidata.org/wiki/Q165194","display_name":"Application programming interface","level":2,"score":0.6714671850204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5008647441864014},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49982261657714844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814528822898865},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.4439719021320343},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.42427128553390503},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4165293872356415},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4105226993560791},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17999666929244995},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s0218194022500449","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500449","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6200000047683716}],"awards":[{"id":"https://openalex.org/G3427093674","display_name":null,"funder_award_id":"62032004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6425072605","display_name":null,"funder_award_id":"62102244","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2099517310","https://openalex.org/W2493916176","https://openalex.org/W2746791238","https://openalex.org/W2767532479","https://openalex.org/W2953163841","https://openalex.org/W2953531182","https://openalex.org/W2964348592","https://openalex.org/W2970168256","https://openalex.org/W3034840004","https://openalex.org/W3103227045","https://openalex.org/W3155407837","https://openalex.org/W3204578495"],"related_works":["https://openalex.org/W2071085159","https://openalex.org/W4249037160","https://openalex.org/W2809632469","https://openalex.org/W4376312358","https://openalex.org/W2111279441","https://openalex.org/W3095243822","https://openalex.org/W1765060747","https://openalex.org/W4285590546","https://openalex.org/W4366976054","https://openalex.org/W3204222276"],"abstract_inverted_index":{"The":[0,68,161],"development":[1],"of":[2,56,109,171,175],"a":[3,168],"question":[4,64],"answering":[5],"(QA)":[6],"system":[7],"for":[8,98,113],"application":[9],"programming":[10],"interface":[11],"(API)":[12],"documentation":[13],"can":[14,40],"greatly":[15],"facilitate":[16],"developers":[17],"in":[18,43,49,135,177],"API-related":[19],"tasks.":[20],"However,":[21],"when":[22],"applying":[23],"deep":[24],"learning":[25,141],"technology,":[26],"API":[27,51,99,178],"QA":[28,100],"systems":[29],"suffer":[30],"from":[31,147],"the":[32,38,50,63,76,107,122,144,148,157],"spurious":[33,73],"solution":[34],"problem.":[35],"That":[36],"is,":[37],"answer":[39],"literally":[41],"appear":[42],"multiple":[44],"positions":[45],"(i.e.":[46],"start-end":[47],"indices)":[48],"documentation,":[52],"though":[53],"only":[54],"one":[55],"them":[57],"(called":[58,72],"golden":[59],"solution)":[60],"correctly":[61],"solves":[62],"given":[65],"its":[66],"context.":[67],"other":[69],"incorrect":[70],"candidates":[71],"solutions)":[74],"hinder":[75],"neural":[77],"network":[78],"model":[79],"to":[80,105,120],"learn":[81],"reasonable":[82],"solutions":[83,111,132],"or":[84],"correct":[85],"answers.":[86],"In":[87,103],"this":[88],"work,":[89],"we":[90,115,138],"propose":[91],"Clean-and-Learn,":[92],"an":[93],"effective":[94],"and":[95,173],"robust":[96],"method":[97,155],"over":[101],"documents.":[102],"order":[104],"reduce":[106],"spuriousness":[108],"candidate":[110,123,131],"used":[112],"training,":[114],"design":[116],"several":[117],"scoring":[118],"functions":[119],"rank":[121],"occurrences":[124,150],"(clean).":[125],"Only":[126],"high-quality":[127],"(top-[Formula:":[128],"see":[129],"text])":[130],"are":[133],"involved":[134],"training.":[136],"Then,":[137],"perform":[139],"multi-task":[140],"by":[142],"weighing":[143],"losses":[145],"computed":[146],"top-k":[149],"(learn).":[151],"We":[152],"evaluate":[153],"our":[154],"on":[156],"constructed":[158],"APIQASet":[159],"dataset.":[160],"experiment":[162],"results":[163],"show":[164],"that":[165],"Clean-and-Learn":[166],"achieves":[167],"ROUGE-L":[169],"score":[170],"75.8":[172],"accuracy":[174],"70.5%":[176],"QA,":[179],"which":[180],"significantly":[181],"outperforms":[182],"state-of-the-art":[183],"approaches.":[184]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-05-05T08:41:31.759640","created_date":"2025-10-10T00:00:00"}